86 citations · 170 across the 21 of their papers we have counts for
23 papers
PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment
Jiawei Feng, Jiancan Wu, Xingyu Zhu +3
Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its adaptation to multimodal se…
Experience Augmented Policy Optimization for LLM Reasoning
Jinda Lu, Kexin Huang, Junkang Wu +7
Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). However, existing RLVR method…
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
Kexin Huang, Junkang Wu, Jinda Lu +7
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this wor…
R^2-Mem: Reflective Experience for Memory Search
Xinyuan Wang, Wenyu Mao, Junkang Wu +2
Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing dee…
Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR
Jinda Lu, Junkang Wu, Jinghan Li +6
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and…
Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs
Jinda Lu, Junkang Wu, Jinghan Li +6
Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave per…
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
Kexin Huang, Haoming Meng, Junkang Wu +10
Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-ind…
Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
Junkang Wu, Kexin Huang, Jiancan Wu +3
Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both haz…
Robust Preference Optimization via Dynamic Target Margins
Jie Sun, Junkang Wu, Jiancan Wu +5
The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an…
RePO: Understanding Preference Learning Through ReLU-Based Optimization
Junkang Wu, Kexin Huang, Xue Wang +5
Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. Whil…
Larger or Smaller Reward Margins to Select Preferences for Alignment?
Kexin Huang, Junkang Wu, Ziqian Chen +6
Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While e…
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
Jinda Lu, Junkang Wu, Jinghan Li +6
Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbal…
LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
Jie Sun, Tianyu Zhang, Houcheng Jiang +11
Auctions are a vital economic mechanism used to determine the market value of goods or services through competitive bidding within a specific framework. However, much of the curren…
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
Junkang Wu, Xue Wang, Zhengyi Yang +5
Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a pop…
-DPO: Direct Preference Optimization with Dynamic
Junkang Wu, Yuexiang Xie, Zhengyi Yang +5
Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO…
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
Junkang Wu, Yuexiang Xie, Zhengyi Yang +6
This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences…
Direct Multi-Turn Preference Optimization for Language Agents
Wentao Shi, Mengqi Yuan, Junkang Wu +2
Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents. Direct Preference Optimization (DPO) is a promising technique for this adaptation w…
BSL: Understanding and Improving Softmax Loss for Recommendation
Junkang Wu, Jiawei Chen, Jiancan Wu +3
Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendati…
Understanding Contrastive Learning via Distributionally Robust Optimization
Junkang Wu, Jiawei Chen, Jiancan Wu +3
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existi…
On the Theories Behind Hard Negative Sampling for Recommendation
Wentao Shi, Jiawei Chen, Fuli Feng +4
Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improv…
FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion
Wentao Shi, Junkang Wu, Xuezhi Cao +4
Learning hyperbolic embeddings for knowledge graph (KG) has gained increasing attention due to its superiority in capturing hierarchies. However, some important operations in hyper…
Adap-: Adaptively Modulating Embedding Magnitude for Recommendation
Jiawei Chen, Junkang Wu, Jiancan Wu +3
Recent years have witnessed the great successes of embedding-based methods in recommender systems. Despite their decent performance, we argue one potential limitation of these meth…
DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network
Junkang Wu, Wentao Shi, Xuezhi Cao +5
Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks. Although recently…